all InfoSec news
NeuroUnlock: Unlocking the Architecture of Obfuscated Deep Neural Networks. (arXiv:2206.00402v1 [cs.CR])
June 2, 2022, 1:20 a.m. | Mahya Morid Ahmadi, Lilas Alrahis, Alessio Colucci, Ozgur Sinanoglu, Muhammad Shafique
cs.CR updates on arXiv.org arxiv.org
The advancements of deep neural networks (DNNs) have led to their deployment
in diverse settings, including safety and security-critical applications. As a
result, the characteristics of these models have become sensitive intellectual
properties that require protection from malicious users. Extracting the
architecture of a DNN through leaky side-channels (e.g., memory access) allows
adversaries to (i) clone the model, and (ii) craft adversarial attacks. DNN
obfuscation thwarts side-channel-based architecture stealing (SCAS) attacks by
altering the run-time traces of a given DNN …
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Cybersecurity Skills Challenge -- Sponsored by DoD
@ Correlation One | United States
Security Operations Center (SOC) Analyst
@ GK Cybersecurity Group | Remote
Azure Security Architect
@ First Quality | Remote US - Eastern or Central Timezone
Threat Intelligence Analyst
@ Atos | Remote Home, HOME (England & Wales), GB, Remote Hom
Alternance (F/H) Hardening, migration cloud et containerisation d'un application windows
@ Alstom | Villeurbanne, FR
Security Specialist / Analist (CIT)
@ Lely | Maassluis, Netherlands